Artificial Intelligence and Nutrition: A Bibliometric Analysis of Global Research Trends and Thematic Evolution

Background: The integration of Artificial Intelligence (AI) into the field of nutritional sciences has gained considerable momentum in recent years, offering promising opportunities for personalized dietary assessment, nutritional epidemiology, food safety, and public health surveillance, However, despite the escalating volume of literature, a comprehensive understanding of global publication trends, collaborative networks, prominent contributors, and evolving thematic landscapes within this interdisciplinary domain remains limited.

Aims: This study aimed to systematically evaluated the research landscape at the intersection of AI and nutrition utilizing bibliometric techniques to identify publication trends, prolific authors, influential source journals, leading geopolitical contributors and institutions, and emerging research themes.

Methods: A bibliometric evaluation was executed utilizing metadata retrieved from the Scopus database. The search matrix targeted literature published between 2013 and 2023. From an initial pool of 1,167 documents, 350 peer-reviewed publications were retained following the application of strict, predefined inclusion and exclusion criteria based on subject area, language, document type, and thematic relevance. Analytical and visualization protocols—encompassing publication trajectories, citation impacts, international collaboration networks, and keyword co-occurrence maps—were executed using VOSviewer and Microsoft Excel.

Results: The analysis revealed a substantial acceleration in scientific output during the final five years of the study period (2019-2023), highlighting intensified scholarly interest in AI-driven nutritional applications. The United States, China, and India emerged as the primary global contributors. Prominent dissemination outlets included Nutrients, the Journal of Nutrition, and the EFSA Journal. Network clustering identified five primary research fronts: AI-based dietary assessment, public health nutrition, machine learning applications for chronic disease prediction, food safety, and the ethical governance of digital nutritional data. The most robust keyword co-occurrence nodes included “Nutrition,” “Artificial Intelligence,” “Dietary Intake,” and “Machine Learning.”

Conclusions: This bibliometric analysis underscores the rapid evolutionary trajectory and highly multidisciplinary nature of the AI-nutrition interface. The domain is characterized by expanding international collaboration, diversified thematic developments, and a profound integration of AI technologies into foundational nutritional science. These insights elucidate the intellectual architecture of the field, serving as a strategic framework to guide future empirical research, policy formulations, and technological innovation in AI-driven nutrition.